cs.LG（2025-12-24）

📊 共 9 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
1 Assessing the Software Security Comprehension of Large Language Models 系统评估大型语言模型在软件安全理解方面的能力，揭示其知识边界与常见误解。 large language model
2 LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics 提出基于竞争瑞士轮动态系统的LLM综合评估框架，解决静态评估的局限性。 large language model
3 Deadline-Aware Online Scheduling for LLM Fine-Tuning with Spot Market Predictions 提出基于预测的在线调度方法以优化LLM微调成本 foundation model
4 Can Agentic AI Match the Performance of Human Data Scientists? Agentic AI在数据科学中能否匹敌人类专家？领域知识至关重要 large language model
5 RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks RevFFN：利用可逆块实现MoE LLM全参数高效微调 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
6 ReACT-Drug: Reaction-Template Guided Reinforcement Learning for de novo Drug Design ReACT-Drug：基于反应模板引导的强化学习药物设计 reinforcement learning PPO representation learning ✅
7 Model Merging via Multi-Teacher Knowledge Distillation 提出SAMerging，通过多教师知识蒸馏实现模型合并，提升泛化性能。 distillation ✅
8 MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models 提出MiST，通过中阶段科学训练提升化学推理模型性能 reinforcement learning large language model
9 Shared Representation Learning for High-Dimensional Multi-Task Forecasting under Resource Contention in Cloud-Native Backends 提出共享表征学习框架，解决云原生后端高维多任务时序预测难题。 representation learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页